Question

A poll was taken this year asking college students if they considered themselves overweight. A similar poll was taken 5 years ago. Five years ago, a sample of 270 students showed that 120 considered themselves overweight. This year a poll of 300 students showed that 140 considered themselves overweight. At a 5% level of significance, test to see if there is any difference in the proportion of college students who consider themselves overweight between the two polls. What is your conclusion?

Answer 1

At 5% significance level, it is statistically evident that there is nodifference in the proportion of college students who consider themselves overweight between the two poll

Explanation:

Given that a poll was taken this year asking college students if they considered themselves overweight. A similar poll was taken 5 years ago.

Let five years ago be group I X and as of now be group II Y

`H_0: p_x =p_y\\H_a: p_x \\eq p_y`

(Two tailed test at 5% level of significance)

Group I Group II combined p

n 270 300 570

favor 120 140 260

p 0.4444 0.4667 0.4561

Std error for differene =
`\sqrt{(0.4561(1-0.4561))/(570) } \\=0.0209`

p difference = -0.0223

Z statistic = p diff/std error = -1.066

p value =0.2864

Since p value >0.05, we accept null hypothesis.

At 5% significance level, it is statistically evident that there is nodifference in the proportion of college students who consider themselves overweight between the two poll